Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
git clone --depth 1 https://github.com/snakeying/TextumWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/commands/snakeying/textum/split-check1)<a href="https://agentmods.dev/commands/snakeying/textum/split-check1"><img src="https://agentmods.dev/badge/commands/snakeying/textum/split-check1/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/commands/snakeying/textum/split-check1"><img src="https://agentmods.dev/badge/commands/snakeying/textum/split-check1.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00000 | $0.03336 |
| Opus 5.5 | $0.00000 | $0.01334 |
| Sonnet 5.5 | $0.00000 | $0.00667 |
| Haiku 4.5 | $0.00000 | $0.00334 |
Grade A, and why
split-check1 scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 194 lines — stays where its author put it; the contents beside it link to each section on GitHub.
阶段4a: Story 拆分校验（Core / split-check1）
读取：docs/split-plan.yaml、docs/story-*-*.md | 写入：docs/split-check-index-pack.yaml（仅无 FAIL；PASS/DECISION 都写） | 模板：.claude/textum/split-check-index-pack-template.yaml
做“结构/一致性/阈值”校验。
输出（DECISION 不阻断）
- 若存在任何
FAIL（含阈值 FAIL 与门禁 FAIL）：- 输出
FAIL清单（F-001起编号；每条必须包含以下字段）：定位：目标文件（docs/split-plan.yaml或docs/story-N-<slug>.md）+（尽量）YAML 路径/章节名/指标名；避免行号问题：1 句期望：可机械执行的“替换目标/格式”（能推导就写出来）影响：H/M/L修复：只给 1 个动作（通常是“按定位修正对应文件”或“将 SPLIT_REPLAN_PACK 粘贴给 /split-plan 重规划”）
- 若包含阈值 FAIL：紧接着追加且仅追加 1 个
SPLIT_REPLAN_PACK代码块 - 末尾追加：
修正：按 FAIL 清单逐条修复（若包含 SPLIT_REPLAN_PACK：将其粘贴给 /split-plan 重规划；否则修正 docs/story-*-*.md 或 docs/split-plan.yaml）重跑：/split-check1
- 然后结束（不写 pack）
- 输出
- 否则（无 FAIL）：
- 写入
docs/split-check-index-pack.yaml - 若存在任何
DECISION：输出DECISION清单（D-001起编号；每条包含：问题 / 影响 / 建议动作），并在末尾追加：已写入：docs/split-check-index-pack.yaml下一步：/split-check2
- 否则：输出：
PASS已写入：docs/split-check-index-pack.yaml下一步：/split-check2
- 写入
执行步骤（必须按序）
- 解析
docs/split-plan.yaml（只抽取索引）：stories[]：story、n、slug、modules[]、prereq_stories[]api_assignments[]：api、story
- 解析所有
docs/story-*-*.md（只抽取索引 + 机械计数）：- 解析 YAML front-matter（文件首部
--- ... ---），抽取：story/n/slug/titlemodules/prereq_stories/fp_idsrefs.gc_br/refs.prd_br/refs.prd_tbl/refs.prd_apiartifacts.file/artifacts.cfg/artifacts.ext
- 计数口径：
api_refs =refs.prd_api去重后数量tbl_refs =refs.prd_tbl去重后数量feature_points =fp_ids去重后数量acceptance_items =## 验收标准（必填）章节下- [ ]条目数
- 解析 YAML front-matter（文件首部
- 大 Story 阈值（早期短路）：
- 若任一 Story 命中阈值
FAIL：输出FAIL + SPLIT_REPLAN_PACK并结束（不写 pack） - 否则：记录阈值
DECISION（若有），继续执行门禁
- 若任一 Story 命中阈值
- 执行门禁（见下）
- 生成索引交接包（见下），写入
docs/split-check-index-pack.yaml
大 Story 阈值（早期短路）
机械计数口径（必须一致）
对每个 docs/story-N-*.md：
api_refs：YAML front-matterrefs.prd_api去重数量tbl_refs：YAML front-matterrefs.prd_tbl去重数量feature_points：YAML front-matterfp_ids去重数量acceptance_items：## 验收标准（必填）章节下- [ ]条目数
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 1mo ago First seen · 194 lines · 0 tokens per session scan A 22ee322dd720
split-check1 is a command published in the GitHub repository snakeying/Textum (41 stars, last pushed 9mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 3,336 tokens. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other commands, from other repositories
statuswt
You are checking the status of all active worktree task files in the project.
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.